Research for SARIMA and PatchTSMixer Models on the IEA Monthly Statistics Dataset
The rapid evolution of intelligent algorithms has led to their extensive application in time-series forecasting, particularly in predicting electricity consumption. Accurate forecasting is crucial for energy management, policy-making, and ensuring a stable power supply. However, a significant gap ex...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | ITM Web of Conferences |
| Online Access: | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_03011.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206542940504064 |
|---|---|
| author | Hu Yuwei |
| author_facet | Hu Yuwei |
| author_sort | Hu Yuwei |
| collection | DOAJ |
| description | The rapid evolution of intelligent algorithms has led to their extensive application in time-series forecasting, particularly in predicting electricity consumption. Accurate forecasting is crucial for energy management, policy-making, and ensuring a stable power supply. However, a significant gap exists in comparing the predictive performance of traditional machine learning methods with advanced deep learning models using real-world datasets. This study aims to address this gap by evaluating and comparing the prediction accuracy of machine learning and deep learning techniques using the Monthly Electricity Statistics dataset from the International Energy Agency (IEA). The research employs a rigorous experimental design, leveraging models such as ARIMA and PatchTSMixer, with an emphasis on model tuning and performance metrics like MAE, MAPE, and RMSE. The findings reveal that deep learning models, particularly PatchTSMixer, outperform traditional machine learning methods in terms of prediction accuracy, demonstrating their superior capability in capturing complex temporal dependencies in electricity consumption data. These results highlight the potential of deep learning models for enhancing predictive accuracy in time-series forecasting, providing valuable insights for future research and practical applications in energy management. |
| format | Article |
| id | doaj-art-105809512d21456f9fdeb9c550fb9e1a |
| institution | Kabale University |
| issn | 2271-2097 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | ITM Web of Conferences |
| spelling | doaj-art-105809512d21456f9fdeb9c550fb9e1a2025-02-07T08:21:11ZengEDP SciencesITM Web of Conferences2271-20972025-01-01700301110.1051/itmconf/20257003011itmconf_dai2024_03011Research for SARIMA and PatchTSMixer Models on the IEA Monthly Statistics DatasetHu Yuwei0Future Tech, South China University of TechnologyThe rapid evolution of intelligent algorithms has led to their extensive application in time-series forecasting, particularly in predicting electricity consumption. Accurate forecasting is crucial for energy management, policy-making, and ensuring a stable power supply. However, a significant gap exists in comparing the predictive performance of traditional machine learning methods with advanced deep learning models using real-world datasets. This study aims to address this gap by evaluating and comparing the prediction accuracy of machine learning and deep learning techniques using the Monthly Electricity Statistics dataset from the International Energy Agency (IEA). The research employs a rigorous experimental design, leveraging models such as ARIMA and PatchTSMixer, with an emphasis on model tuning and performance metrics like MAE, MAPE, and RMSE. The findings reveal that deep learning models, particularly PatchTSMixer, outperform traditional machine learning methods in terms of prediction accuracy, demonstrating their superior capability in capturing complex temporal dependencies in electricity consumption data. These results highlight the potential of deep learning models for enhancing predictive accuracy in time-series forecasting, providing valuable insights for future research and practical applications in energy management.https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_03011.pdf |
| spellingShingle | Hu Yuwei Research for SARIMA and PatchTSMixer Models on the IEA Monthly Statistics Dataset ITM Web of Conferences |
| title | Research for SARIMA and PatchTSMixer Models on the IEA Monthly Statistics Dataset |
| title_full | Research for SARIMA and PatchTSMixer Models on the IEA Monthly Statistics Dataset |
| title_fullStr | Research for SARIMA and PatchTSMixer Models on the IEA Monthly Statistics Dataset |
| title_full_unstemmed | Research for SARIMA and PatchTSMixer Models on the IEA Monthly Statistics Dataset |
| title_short | Research for SARIMA and PatchTSMixer Models on the IEA Monthly Statistics Dataset |
| title_sort | research for sarima and patchtsmixer models on the iea monthly statistics dataset |
| url | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_03011.pdf |
| work_keys_str_mv | AT huyuwei researchforsarimaandpatchtsmixermodelsontheieamonthlystatisticsdataset |